Data Visualization Using R: Base R, ggplot2 & Plotly

Data Visualization Tutorial in R

Welcome to the Big Data Analysis and Management Training Program

Welcome to the second section of our comprehensive training program! This section provides a comprehensive guide to data visualization in R using three approaches:

1. Base R Graphics - Quick exploratory plots
2. ggplot2 - Publication-quality plots
3. Plotly - Interactive web-based plots

Each section progresses from simple to complex examples with detailed explanations of function arguments.

---

Section 1: BASE R GRAPHICS

1.1 Basic Plot Function

# Load built-in dataset
data(mtcars)

# Display dataset information
cat(
  "Dataset: mtcars (Motor Trend Car Road Tests)\n",
  "Rows:", nrow(mtcars), "| Columns:", ncol(mtcars), "\n\n",
  "First 6 rows:\n",
  sep = ""
)

## Dataset: mtcars (Motor Trend Car Road Tests)
## Rows:32| Columns:11
## 
## First 6 rows:

print(head(mtcars))

##                    mpg cyl disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
## Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

1.2 Simple Black & White Scatter Plot

# Basic scatter plot with minimal arguments
plot(mtcars$wt,           # x variable: car weight
     mtcars$mpg,          # y variable: miles per gallon
     main = "Weight vs MPG",  # main: plot title
     xlab = "Weight (1000 lbs)",  # xlab: x-axis label
     ylab = "Miles per Gallon",   # ylab: y-axis label
     pch = 16,            # pch: point character (16 = filled circle)
     col = "black",       # col: point color
     cex = 1.0,           # cex: character expansion (point size)
     frame = FALSE)       # frame: remove box around plot

1.3 Adding Color and Customization

# Create color vector based on number of cylinders
colors <- ifelse(mtcars$cyl == 4, "red",
                ifelse(mtcars$cyl == 6, "green", "blue"))

# Enhanced scatter plot with colors and sizes
plot(mtcars$wt, mtcars$mpg,
     main = "Weight vs MPG (Colored by Cylinders)",
     xlab = "Weight (1000 lbs)",
     ylab = "Miles per Gallon",
     pch = ifelse(mtcars$cyl == 4, 16,      # Different shapes for different cylinders
                  ifelse(mtcars$cyl == 6, 17, 18)),
     col = colors,        # Use custom color vector
     cex = ifelse(mtcars$cyl == 4, 1.0,     # Different sizes based on cylinders
                  ifelse(mtcars$cyl == 6, 1.3, 1.6)),
     frame = FALSE,
     lwd = 1.5)           # lwd: line width for point borders

# Add legend
legend("topright",                     # Position: top right corner
       legend = c("4 Cylinders", "6 Cylinders", "8 Cylinders"),  # Text labels
       col = c("red", "green", "blue"), # Colors
       pch = c(16, 17, 18),            # Point characters
       pt.cex = c(1.0, 1.3, 1.6),      # Point sizes
       title = "Cylinders",            # Legend title
       bty = "n")                      # bty: box type ("n" = no box)

1.4 Adding Regression Line and Grid

# Plot with regression line and grid
plot(mtcars$wt, mtcars$mpg,
     main = "Weight vs MPG with Regression Line",
     xlab = "Weight (1000 lbs)",
     ylab = "Miles per Gallon",
     pch = 16,
     col = rgb(0.2, 0.4, 0.8, 0.7),  # RGB colors with transparency (alpha = 0.7)
     cex = 1.2,
     frame = FALSE)

# Add grid lines
grid(col = "gray",        # Grid color
     lty = "dotted",      # lty: line type ("dotted", "dashed", "solid")
     lwd = 0.5)           # lwd: line width

# Add regression line using abline()
abline(lm(mpg ~ wt, data = mtcars),  # Linear model
       col = "red",                   # Line color
       lwd = 2,                       # Line width
       lty = "dashed")                # Line type: dashed

# Add text annotation
text(x = 4.5, y = 30,                # x, y: coordinates for text
     labels = "Negative Correlation", # Text to display
     col = "darkred",                 # Text color
     cex = 1.1)                       # Text size

1.5 Using par() for Multiple Plots

# Save current par settings
old_par <- par()

# Set up 2x2 plot grid
par(mfrow = c(2, 2),        # mfrow: matrix of plots (rows, columns)
    mar = c(4, 4, 3, 1),    # mar: margins (bottom, left, top, right)
    oma = c(2, 2, 2, 0))    # oma: outer margins

# Plot 1: Basic scatter
plot(mtcars$wt, mtcars$mpg,
     main = "Basic Scatter",
     xlab = "Weight",
     ylab = "MPG",
     pch = 16,
     col = "steelblue")

# Plot 2: With regression line
plot(mtcars$wt, mtcars$mpg,
     main = "With Regression",
     xlab = "Weight",
     ylab = "MPG",
     pch = 16,
     col = "forestgreen")
abline(lm(mpg ~ wt, data = mtcars), col = "red", lwd = 2)

# Plot 3: Color by cylinders
colors <- c("red", "green", "blue")[as.factor(mtcars$cyl)]
plot(mtcars$wt, mtcars$mpg,
     main = "By Cylinders",
     xlab = "Weight",
     ylab = "MPG",
     pch = 16,
     col = colors)

# Plot 4: With smooth curve
plot(mtcars$wt, mtcars$mpg,
     main = "With Smooth Curve",
     xlab = "Weight",
     ylab = "MPG",
     pch = 16,
     col = "purple")
lines(lowess(mtcars$wt, mtcars$mpg),  # LOWESS smoother
      col = "orange",
      lwd = 2)

# Add overall title
mtext("Multiple Views of Weight vs MPG",  # Text to display
      side = 3,                           # side: 3 = top
      outer = TRUE,                       # Place in outer margin
      cex = 1.5,                          # Text size
      font = 2)                           # Font: 2 = bold

# Reset to original par settings
par(old_par)

1.6 Histograms with Base R

# Load faithful dataset
data(faithful)

# Display dataset info
cat("Dataset: faithful (Old Faithful Geyser)\n")

## Dataset: faithful (Old Faithful Geyser)

cat("Rows:", nrow(faithful), "\n\n")

## Rows: 272

print(head(faithful))

##   eruptions waiting
## 1     3.600      79
## 2     1.800      54
## 3     3.333      74
## 4     2.283      62
## 5     4.533      85
## 6     2.883      55

# Set up 1x2 plot layout
par(mfrow = c(1, 2))

# Basic histogram
hist(faithful$waiting,          # Data vector
     main = "Basic Histogram",  # Title
     xlab = "Waiting Time (min)", # x-axis label
     ylab = "Frequency",        # y-axis label
     col = "lightblue",         # Fill color
     border = "white",          # Border color
     breaks = 15,               # Number of bins
     freq = TRUE)               # freq: TRUE for frequency, FALSE for density

# Histogram with density curve
hist(faithful$waiting,
     main = "With Density Curve",
     xlab = "Waiting Time (min)",
     ylab = "Density",
     col = rgb(0.8, 0.9, 1, 0.6),  # Light blue with transparency
     border = "navy",
     freq = FALSE,                  # Plot density instead of frequency
     breaks = 20)

# Add density curve
lines(density(faithful$waiting),  # Density estimation
      col = "darkred",            # Line color
      lwd = 2)                    # Line width

# Add rug plot (shows individual data points)
rug(faithful$waiting,             # Data points
    side = 1,                     # side: 1 = bottom
    col = "red",                  # Color
    lwd = 0.5)                    # Line width

# Reset layout
par(mfrow = c(1, 1))

1.7 Box Plots

# Load ToothGrowth dataset
data(ToothGrowth)

# Display dataset info
cat("Dataset: ToothGrowth\n")

## Dataset: ToothGrowth

cat("Rows:", nrow(ToothGrowth), "\n")

## Rows: 60

print(head(ToothGrowth))

##    len supp dose
## 1  4.2   VC  0.5
## 2 11.5   VC  0.5
## 3  7.3   VC  0.5
## 4  5.8   VC  0.5
## 5  6.4   VC  0.5
## 6 10.0   VC  0.5

# Create box plot
boxplot(len ~ supp,            # Formula: length by supplement type
        data = ToothGrowth,    # Data source
        main = "Tooth Growth by Supplement",  # Title
        xlab = "Supplement Type",             # x-axis label
        ylab = "Tooth Length",                # y-axis label
        col = c("lightblue", "lightgreen"),   # Colors for groups
        border = "darkblue",                  # Box border color
        notch = TRUE,                         # notch: add notches for median comparison
        outpch = 16,                          # outpch: outlier point character
        outcol = "red",                       # outcol: outlier color
        outcex = 1.2)                         # outcex: outlier size

# Add points for individual data
stripchart(len ~ supp,          # Formula
           data = ToothGrowth,  # Data
           vertical = TRUE,     # vertical: TRUE for vertical orientation
           method = "jitter",   # method: "jitter" to spread points
           pch = 16,            # Point character
           col = rgb(0, 0, 0, 0.3),  # Semi-transparent black
           cex = 0.8,           # Point size
           add = TRUE)          # add: add to existing plot

1.8 Time Series Plot

# Load AirPassengers dataset
data(AirPassengers)

# Display dataset info
cat("Dataset: AirPassengers (Monthly totals 1949-1960)\n")

## Dataset: AirPassengers (Monthly totals 1949-1960)

print(str(AirPassengers))

##  Time-Series [1:144] from 1949 to 1961: 112 118 132 129 121 135 148 148 136 119 ...
## NULL

print(head(AirPassengers))

##      Jan Feb Mar Apr May Jun
## 1949 112 118 132 129 121 135

# Basic time series plot
plot(AirPassengers,             # Time series object
     main = "Airline Passengers Over Time",  # Title
     xlab = "Year",                         # x-axis label
     ylab = "Passengers (thousands)",       # y-axis label
     type = "l",                # type: "l" = line plot
     col = "blue",              # Line color
     lwd = 2,                   # Line width
     las = 1)                   # las: axis label style (1 = horizontal)

# Add seasonal decomposition lines
decomp <- decompose(AirPassengers)
lines(decomp$trend,             # Trend component
      col = "red",              # Color
      lwd = 2,                  # Line width
      lty = "dashed")           # Line type

# Add legend
legend("topleft",               # Position
       legend = c("Original", "Trend"),  # Labels
       col = c("blue", "red"),  # Colors
       lwd = c(2, 2),           # Line widths
       lty = c("solid", "dashed"),  # Line types
       bty = "n")               # No box around legend

1.9 Base R Exercises

# EXERCISE 1: Create a scatter plot of Sepal.Length vs Sepal.Width from iris dataset
# Requirements:
# 1. Color points by Species
# 2. Add a legend
# 3. Add a title and axis labels
# 4. Add a grid

# EXERCISE 2: Create a histogram of Petal.Length from iris dataset
# Requirements:
# 1. Use different colors for each Species
# 2. Add density curves
# 3. Add appropriate title and labels

# EXERCISE 3: Create a 2x2 plot matrix showing:
# 1. Box plot of mpg by cylinder count
# 2. Histogram of mpg
# 3. Scatter plot of hp vs mpg
# 4. Bar plot of cylinder counts

---

Section 2: GGPLOT2 VISUALIZATION

print(str(iris))

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
## NULL

print(head(iris))

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa

2.1 Introduction to ggplot2

ggplot2 is based on the “Grammar of Graphics” - a systematic approach to building plots layer by layer.

# Basic ggplot2 syntax structure
cat("ggplot2 Basic Syntax:\n",
    "ggplot(data, aes(x, y)) +           # Initialize plot\n",
    "  geom_layer() +                    # Add geometry\n",
    "  scale_*() +                       # Customize scales\n",
    "  theme_*() +                       # Apply theme\n",
    "  labs()                            # Add labels\n",
    sep = "")

## ggplot2 Basic Syntax:
## ggplot(data, aes(x, y)) +           # Initialize plot
##   geom_layer() +                    # Add geometry
##   scale_*() +                       # Customize scales
##   theme_*() +                       # Apply theme
##   labs()                            # Add labels

2.2 Basic ggplot Scatter Plot

# Load iris dataset
data(iris)

# Basic ggplot scatter plot
ggplot(iris,                               # data: dataset
       aes(x = Sepal.Length,               # aes: aesthetic mappings
           y = Sepal.Width,                # x and y variables
           color = Species)) +             # color: map Species to color
  geom_point(size = 3,                     # geom_point: scatter plot layer
             alpha = 0.7) +                # alpha: transparency (0-1)
  labs(title = "Sepal Length vs Width",    # labs: labels and titles
       subtitle = "Iris Dataset",
       x = "Sepal Length (cm)",
       y = "Sepal Width (cm)",
       color = "Species") +                # Legend title
  theme_minimal() +                        # theme: minimal theme
  theme(plot.title = element_text(hjust = 0.5),    # Center title
        plot.subtitle = element_text(hjust = 0.5)) # Center subtitle

2.3 ggplot with Multiple Geometries

# Plot with multiple geometry layers
ggplot(iris, aes(x = Sepal.Length, y = Sepal.Width, color = Species)) +
  geom_point(size = 3,                    # First layer: points
             alpha = 0.6) +
  geom_smooth(method = "lm",              # Second layer: linear regression
              se = TRUE,                  # se: show confidence interval
              formula = y ~ x,            # Formula for smoothing
              alpha = 0.2) +              # Transparency for confidence band
  geom_density_2d(alpha = 0.5,            # Third layer: 2D density contours
                  color = "black") +
  facet_wrap(~ Species,                   # facet_wrap: separate plots by Species
             ncol = 3) +                  # ncol: number of columns
  labs(title = "Sepal Dimensions with Regression",
       x = "Sepal Length (cm)",
       y = "Sepal Width (cm)") +
  theme_bw() +                            # Black and white theme
  theme(legend.position = "none")         # Hide legend (redundant with facets)

2.4 Histograms and Density Plots with ggplot

# Create comparison plot
p1 <- ggplot(faithful, aes(x = waiting)) +
  geom_histogram(binwidth = 5,            # binwidth: width of bins
                 fill = "lightblue",      # fill: interior color
                 color = "black",         # color: border color
                 alpha = 0.7) +           # alpha: transparency
  labs(title = "Histogram", 
       x = "Waiting Time (min)", 
       y = "Count") +
  theme_minimal()

p2 <- ggplot(faithful, aes(x = waiting)) +
  geom_density(fill = "lightgreen",       # Density plot fill
               alpha = 0.5, 
               color = "darkgreen") +
  labs(title = "Density Plot",
       x = "Waiting Time (min)", 
       y = "Density") +
  theme_minimal()

p3 <- ggplot(faithful, aes(x = waiting)) +
  geom_histogram(aes(y = ..density..),    # ..density..: use density instead of count
                 binwidth = 5,
                 fill = "lightcoral",
                 alpha = 0.5) +
  geom_density(color = "darkred", 
               size = 1) +                # size: line thickness
  labs(title = "Histogram + Density",
       x = "Waiting Time (min)", 
       y = "Density") +
  theme_minimal()

# Arrange plots using patchwork (install if needed: install.packages("patchwork"))
if(require(patchwork)) {
  p1 + p2 + p3 + plot_layout(ncol = 3)
} else {
  print(p1)
  print(p2)
  print(p3)
}

2.5 Box Plots and Violin Plots

# Create ToothGrowth plot
ggplot(ToothGrowth, 
       aes(x = factor(dose),          # factor(): treat dose as categorical
           y = len, 
           fill = factor(dose))) +    # fill: map dose to fill color
  geom_violin(alpha = 0.6,            # Violin plot
              trim = FALSE) +         # trim: don't trim tails
  geom_boxplot(width = 0.2,           # Box plot inside violin
               alpha = 0.8) +    
  geom_jitter(width = 0.1,            # Jittered points
              size = 1.5, 
              alpha = 0.5) +
  labs(title = "Tooth Growth by Dose",
       subtitle = "Violin + Box + Jitter Plot",
       x = "Dose (mg/day)",
       y = "Tooth Length",
       fill = "Dose") +
  scale_fill_brewer(palette = "Set2") +  # ColorBrewer palette
  theme_classic()                      # Classic theme

2.6 Bar Plots

# Prepare Titanic data
titanic_df <- as.data.frame(Titanic)
print(head(titanic_df))

##   Class    Sex   Age Survived Freq
## 1   1st   Male Child       No    0
## 2   2nd   Male Child       No    0
## 3   3rd   Male Child       No   35
## 4  Crew   Male Child       No    0
## 5   1st Female Child       No    0
## 6   2nd Female Child       No    0

# Bar plot
ggplot(titanic_df, 
       aes(x = Class,                  # x: categorical variable
           y = Freq,                   # y: frequency
           fill = Survived)) +         # fill: color by survival
  geom_bar(stat = "identity",          # stat: use actual y values
           position = "dodge",         # position: bars side by side
           width = 0.7) +              # width: bar width (0-1)
  
  labs(title = "Titanic Survival by Class",
       x = "Passenger Class",
       y = "Count",
       fill = "Survived") +
  scale_fill_manual(values = c("Yes" = "#4daf4a", "No" = "#e41a1c")) +  # Custom colors
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))  # Rotate x labels

2.7 Heatmaps

# Prepare volcano data
print(head(volcano))

##      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13] [,14]
## [1,]  100  100  101  101  101  101  101  100  100   100   101   101   102   102
## [2,]  101  101  102  102  102  102  102  101  101   101   102   102   103   103
## [3,]  102  102  103  103  103  103  103  102  102   102   103   103   104   104
## [4,]  103  103  104  104  104  104  104  103  103   103   103   104   104   104
## [5,]  104  104  105  105  105  105  105  104  104   103   104   104   105   105
## [6,]  105  105  105  106  106  106  106  105  105   104   104   105   105   106
##      [,15] [,16] [,17] [,18] [,19] [,20] [,21] [,22] [,23] [,24] [,25] [,26]
## [1,]   102   102   103   104   103   102   101   101   102   103   104   104
## [2,]   103   103   104   105   104   103   102   102   103   105   106   106
## [3,]   104   104   105   106   105   104   104   105   106   107   108   110
## [4,]   105   105   106   107   106   106   106   107   108   110   111   114
## [5,]   105   106   107   108   108   108   109   110   112   114   115   118
## [6,]   106   107   109   110   110   112   113   115   116   118   119   121
##      [,27] [,28] [,29] [,30] [,31] [,32] [,33] [,34] [,35] [,36] [,37] [,38]
## [1,]   105   107   107   107   108   108   110   110   110   110   110   110
## [2,]   107   109   110   110   110   110   111   112   113   114   116   115
## [3,]   111   113   114   115   114   115   116   118   119   119   121   121
## [4,]   117   118   117   119   120   121   122   124   125   126   127   127
## [5,]   121   122   121   123   128   131   129   130   131   131   132   132
## [6,]   124   126   126   129   134   137   137   136   136   135   136   136
##      [,39] [,40] [,41] [,42] [,43] [,44] [,45] [,46] [,47] [,48] [,49] [,50]
## [1,]   110   110   108   108   108   107   107   108   108   108   108   108
## [2,]   114   112   110   110   110   109   108   109   109   109   109   108
## [3,]   120   118   116   114   112   111   110   110   110   110   109   109
## [4,]   126   124   122   120   117   116   113   111   110   110   110   109
## [5,]   131   130   128   126   122   119   115   114   112   110   110   110
## [6,]   136   135   133   129   126   122   118   116   115   113   111   110
##      [,51] [,52] [,53] [,54] [,55] [,56] [,57] [,58] [,59] [,60] [,61]
## [1,]   107   107   107   107   106   106   105   105   104   104   103
## [2,]   108   108   108   107   107   106   106   105   105   104   104
## [3,]   109   109   108   108   107   107   106   106   105   105   104
## [4,]   109   109   109   108   108   107   107   106   106   105   105
## [5,]   110   110   109   109   108   107   107   107   106   106   105
## [6,]   110   110   110   109   108   108   108   107   107   106   106

volcano_long <- reshape2::melt(volcano)
print(head(volcano_long))

##   Var1 Var2 value
## 1    1    1   100
## 2    2    1   101
## 3    3    1   102
## 4    4    1   103
## 5    5    1   104
## 6    6    1   105

# Colors in R
par(mfrow=c(1,5)); z <- matrix(volcano, nrow(volcano)); 
lapply(list(terrain.colors, 
            topo.colors, 
            heat.colors, 
            cm.colors, 
            rainbow), \(f) image(z, col=f(100), axes=FALSE))

# Heatmap with ggplot
ggplot(volcano_long, 
       aes(x = Var1,                   # x coordinate
           y = Var2,                   # y coordinate
           fill = value)) +            # fill: color by value
  geom_tile() +                        # geom_tile: creates heatmap
  scale_fill_gradientn(colors = terrain.colors(10),  # Color gradient
                       name = "Height") +            # Legend title
  labs(title = "Volcano Topography Heatmap",
       x = "X Coordinate",
       y = "Y Coordinate") +
  theme_minimal() +
  theme(panel.grid = element_blank())  # Remove grid lines

2.8 Custom Themes and Saving Plots

# Create custom plot
custom_plot <- ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
  geom_boxplot(alpha = 0.8,
               outlier.color = "red",
               outlier.size = 2) +
  geom_jitter(width = 0.2, 
              size = 1.5, 
              alpha = 0.4) +
  labs(title = "Sepal Length by Species",
       subtitle = "Iris Dataset Analysis",
       x = "Species",
       y = "Sepal Length (cm)",
       caption = "Source: Fisher's Iris Dataset") +
  scale_fill_brewer(palette = "Set3") +
  
  # Custom theme
  theme(
    plot.title = element_text(size = 16,           # Title size
                              face = "bold",       # Font face
                              hjust = 0.5),       # Horizontal justification
    plot.subtitle = element_text(size = 12,
                                 hjust = 0.5),
    axis.title = element_text(size = 12,           # Axis title size
                              face = "bold"),
    axis.text = element_text(size = 10),          # Axis text size
    legend.title = element_text(face = "bold"),
    legend.position = "bottom",                   # Legend position
    panel.background = element_rect(fill = "white"),  # Panel background
    panel.grid.major = element_line(color = "gray90",  # Major grid lines
                                    size = 0.5),
    panel.grid.minor = element_blank(),           # Remove minor grid
    plot.background = element_rect(fill = "white",  # Plot background
                                   color = "black",
                                   size = 1)
  )

print(custom_plot)

# Save plot
ggsave("figures/custom_ggplot.png",        # filename
       plot = custom_plot,                 # plot to save
       width = 10,                         # width in inches
       height = 6,                         # height in inches
       dpi = 300)                          # resolution

2.9 ggplot2 Exercises

# EXERCISE 4: Create a ggplot of mtcars showing:
# 1. Scatter plot of mpg vs hp
# 2. Color points by transmission type (am)
# 3. Add smooth trend line
# 4. Facet by number of cylinders
# 5. Apply theme_classic()

# EXERCISE 5: Create a bar plot of diamond counts by cut
# 1. Use diamonds dataset (ggplot2::diamonds)
# 2. Fill bars by color
# 3. Use position = "fill" for proportions
# 4. Add percentage labels

# EXERCISE 6: Create a line plot of economics dataset
# 1. Plot unemployment rate over time
# 2. Add vertical line for significant events
# 3. Add shaded region for recession periods
# 4. Use scale_x_date() for proper date formatting

---

Section 3: PLOTLY INTERACTIVE VISUALIZATION

3.1 Introduction to Plotly

# Basic plotly syntax
cat(
  "plotly Basic Syntax:\n",
  "plot_ly(data, x = ~var1, y = ~var2, type = 'scatter', mode = 'markers')\n",
  "\nCommon type values:\n",
  "- 'scatter': scatter/line plots\n",
  "- 'bar': bar charts\n",
  "- 'histogram': histograms\n",
  "- 'box': box plots\n",
  "- 'heatmap': heatmaps\n",
  sep = ""
)

## plotly Basic Syntax:
## plot_ly(data, x = ~var1, y = ~var2, type = 'scatter', mode = 'markers')
## 
## Common type values:
## - 'scatter': scatter/line plots
## - 'bar': bar charts
## - 'histogram': histograms
## - 'box': box plots
## - 'heatmap': heatmaps

3.2 Basic Interactive Scatter Plot

# Basic interactive scatter plot
p <- plot_ly(mtcars,                      # data: dataset
             x = ~wt,                     # x: weight (~ means formula)
             y = ~mpg,                    # y: mpg
             type = 'scatter',            # type: plot type
             mode = 'markers',            # mode: display mode
             marker = list(size = 10,     # marker: point properties
                           color = 'rgba(30, 120, 180, 0.8)',  # RGBA color
                           line = list(color = 'rgb(0,0,0)',   # Border color
                                       width = 1)),            # Border width
             text = ~paste('Car:', rownames(mtcars),  # text: hover text
                           '<br>MPG:', mpg,
                           '<br>Weight:', wt),
             hoverinfo = 'text') %>%      # hoverinfo: what to show on hover
  layout(title = 'Interactive Scatter Plot',  # layout: plot layout
         xaxis = list(title = 'Weight (1000 lbs)'),  # xaxis properties
         yaxis = list(title = 'Miles per Gallon'),   # yaxis properties
         hovermode = 'closest')           # hovermode: how hover works

p

3.3 Colored Scatter with Legend

# Colored scatter plot with groups
p <- plot_ly(mtcars,
             x = ~wt,
             y = ~mpg,
             color = ~factor(cyl),        # color: map to color scale
             colors = c('#e41a1c', '#377eb8', '#4daf4a'),  # Custom colors
             type = 'scatter',
             mode = 'markers',
             size = ~hp,                  # size: map to point size
             sizes = c(5, 20),            # sizes: min and max size
             marker = list(opacity = 0.7, # opacity: transparency
                           sizemode = 'diameter'),  # sizemode: how to interpret size
             text = ~paste('Car:', rownames(mtcars),
                           '<br>Cylinders:', cyl,
                           '<br>HP:', hp),
             hoverinfo = 'text') %>%
  layout(title = 'Weight vs MPG (Interactive)',
         xaxis = list(title = 'Weight'),
         yaxis = list(title = 'MPG'),
         legend = list(title = list(text = 'Cylinders')),  # Legend title
         hovermode = 'closest')

p

3.4 3D Scatter Plot

# Interactive 3D scatter plot
p <- plot_ly(mtcars,
             x = ~wt,
             y = ~mpg,
             z = ~hp,                     # z: third dimension
             color = ~factor(cyl),
             colors = c('#ff7f00', '#984ea3', '#ffff33'),
             type = 'scatter3d',          # type: 3D scatter
             mode = 'markers',
             marker = list(size = 5,
                           opacity = 0.8),
             text = ~rownames(mtcars)) %>%
  layout(title = '3D Scatter Plot',
         scene = list(                    # scene: 3D scene properties
           xaxis = list(title = 'Weight'),
           yaxis = list(title = 'MPG'),
           zaxis = list(title = 'Horsepower'),
           camera = list(                 # camera: viewing angle
             eye = list(x = 1.5, y = 1.5, z = 1.5)  # eye position
           )
         ))

p

3.5 Interactive Time Series

# Create time series data
dates <- seq.Date(from = as.Date('2020-01-01'), 
                  by = 'month', 
                  length.out = 24)
sales <- cumsum(rnorm(24, mean = 100, sd = 20))

# Interactive line plot
p <- plot_ly(x = dates,                   # x: dates
             y = sales,                    # y: sales
             type = 'scatter',
             mode = 'lines+markers',      # mode: lines and markers
             line = list(color = 'rgb(31, 119, 180)',  # line properties
                         width = 2,
                         dash = 'solid'),
             marker = list(size = 8,
                           color = 'rgb(255, 127, 14)'),
             name = 'Sales') %>%          # name: trace name
  layout(title = 'Sales Over Time',
         xaxis = list(title = 'Date',
                      type = 'date',      # type: date axis
                      tickformat = '%b %Y'),  # Date format
         yaxis = list(title = 'Sales ($)'),
         hovermode = 'x unified')         # Show all y values at x position

p

3.6 Interactive Bar Plot

# Prepare Titanic data for plotly
titanic_summary <- aggregate(Freq ~ Class + Survived, 
                            data = titanic_df, 
                            sum)

# Interactive bar plot
p <- plot_ly(titanic_summary,
             x = ~Class,
             y = ~Freq,
             color = ~Survived,
             colors = c('#d7191c', '#2c7bb6'),
             type = 'bar',
             text = ~Freq,
             textposition = 'auto',       # textposition: auto position text
             hovertext = ~paste('Class:', Class,  # hovertext: custom hover
                               '<br>Survived:', Survived,
                               '<br>Count:', Freq),
             hoverinfo = 'text') %>%
  layout(title = 'Titanic Survival by Class',
         xaxis = list(title = 'Passenger Class'),
         yaxis = list(title = 'Count'),
         barmode = 'group',               # barmode: grouped bars
         bargap = 0.15,                   # bargap: gap between bars
         bargroupgap = 0.1,               # bargroupgap: gap between groups
         hoverlabel = list(namelength = -1))  # Show full hover label

p

3.7 Interactive Histogram

# Interactive histogram
p <- plot_ly(x = faithful$waiting,
             type = 'histogram',
             nbinsx = 20,                 # nbinsx: number of bins
             marker = list(color = 'rgb(158,202,225)',  # Bar color
                           line = list(color = 'rgb(8,48,107)',  # Border color
                                       width = 1.5)),
             opacity = 0.7,               # opacity: transparency
             name = 'Waiting Time') %>%   # name: legend name
  layout(title = 'Waiting Time Distribution',
         xaxis = list(title = 'Waiting Time (minutes)',
                      range = c(40, 100)),  # range: axis range
         yaxis = list(title = 'Count'),
         bargap = 0.05,                   # bargap: gap between bars
         hovermode = 'x')                 # Show histogram bin info

p

3.8 Plotly Exercises

# EXERCISE 7: Create an interactive plot of quakes dataset
# 1. 2D scatter of lat vs long
# 2. Color by depth
# 3. Size by magnitude
# 4. Add hover information with all variables

# EXERCISE 8: Create interactive volcano surface plot
# 1. Use plot_ly type = "surface"
# 2. Add contours
# 3. Customize colorscale
# 4. Add lighting effects

# EXERCISE 9: Create dashboard with subplots
# 1. Combine scatter, histogram, and box plot
# 2. Link selections between plots
# 3. Add dropdown menus for variable selection

---

Section 4: BEST PRACTICES AND COMPARISON

4.1 When to Use Each Tool

# Create comparison data frame
comparison <- data.frame(
  Feature = c("Learning Curve", "Customization", "Interactivity", 
              "Publication Quality", "Speed", "Ease of Use"),
  Base_R = c("Easy", "Basic", "None", "Basic", "Fast", "Very Easy"),
  ggplot2 = c("Moderate", "Excellent", "Limited", "Excellent", "Moderate", "Moderate"),
  Plotly = c("Steep", "Good", "Excellent", "Good", "Slow", "Complex")
)

# Display as interactive table
DT::datatable(comparison,
              options = list(pageLength = 6, 
                             dom = 't'),
              rownames = FALSE) %>%
  DT::formatStyle(columns = 1:4, 
                  fontSize = '12px')

4.2 Color Palette Best Practices

# Show different color palettes
par(mfrow = c(1, 3), mar = c(2, 2, 2, 1))

# Sequential palette (for ordered data)
image(volcano[1:10, 1:10], 
      col = brewer.pal(9, "Blues"),
      main = "Sequential (Blues)")

# Diverging palette (for data with midpoint)
image(volcano[1:10, 1:10] - mean(volcano[1:10, 1:10]), 
      col = brewer.pal(11, "RdBu"),
      main = "Diverging (RdBu)")

# Qualitative palette (for categorical data)
barplot(rep(1, 8), 
        col = brewer.pal(8, "Set3"),
        main = "Qualitative (Set3)",
        border = NA)

par(mfrow = c(1, 1))

4.3 Exporting Plots

# Export Base R plot
png("figures/base_scatter.png",    # filename
    width = 2000,                  # width in pixels
    height = 1500,                 # height in pixels
    res = 300)                     # resolution (DPI)
plot(mtcars$wt, mtcars$mpg,
     main = "Exported Plot",
     xlab = "Weight",
     ylab = "MPG")
dev.off()

# Export ggplot
ggsave("figures/ggplot_export.png",
       plot = custom_plot,
       width = 10,     # inches
       height = 6,     # inches
       dpi = 300)

# Export plotly (as HTML)
htmlwidgets::saveWidget(p, "figures/plotly_export.html")

4.4 Performance Tips

cat("Performance Optimization Tips:\n\n",
    "• For large datasets (>10k points):\n",
    "  - Use hexbin plots or 2D density\n",
    "  - Sample data for initial exploration\n",
    "  - Consider data aggregation\n\n",
    "• Memory management:\n",
    "  - Remove unused objects: rm(object)\n",
    "  - Clear plots: dev.off()\n",
    "  - Run garbage collection: gc()\n\n",
    "• Plotting speed:\n",
    "  - Base R: fastest for simple plots\n",
    "  - ggplot2: slower, more features\n",
    "  - Plotly: slowest, but interactive\n"
)

## Performance Optimization Tips:
## 
##  • For large datasets (>10k points):
##    - Use hexbin plots or 2D density
##    - Sample data for initial exploration
##    - Consider data aggregation
## 
##  • Memory management:
##    - Remove unused objects: rm(object)
##    - Clear plots: dev.off()
##    - Run garbage collection: gc()
## 
##  • Plotting speed:
##    - Base R: fastest for simple plots
##    - ggplot2: slower, more features
##    - Plotly: slowest, but interactive

---

FINAL PROJECT

# FINAL PROJECT: Create a Visualization Dashboard
# 
# Choose any dataset (suggestions: gapminder, diamonds, economics)
# 
# Requirements:
# 1. Create at least 3 different plot types
# 2. Use all three plotting systems (Base R, ggplot2, Plotly)
# 3. Include:
#    - Proper labels and titles
#    - Legends where appropriate
#    - Color schemes
#    - Theme customization
# 
# 4. Export all plots
# 5. Write brief analysis of findings
# 
# Example workflow:
# 1. Load and explore data
# 2. Create Base R plots for quick exploration
# 3. Create ggplot2 plots for publication
# 4. Create Plotly plots for interactivity
# 5. Compare insights from different visualizations

---

SUMMARY

Key Takeaways

1. Base R is best for quick exploratory analysis and simple plots
2. ggplot2 excels at creating publication-quality, complex visualizations
3. Plotly is ideal for interactive, web-based dashboards
4. Always consider your audience and purpose when choosing a plotting method
5. Good visualizations tell a story - use titles, labels, and annotations effectively

Additional Resources

• R Graph Gallery: https://r-graph-gallery.com/
• ggplot2 Documentation: https://ggplot2.tidyverse.org/
• Plotly R Documentation: https://plotly.com/r/
• ColorBrewer: https://colorbrewer2.org/
• Data Visualization Checklist: https://stephanieevergreen.com/av-checklist/

---

This material is part of the training program by The National Centre for Research Methods © NCRM authored by Dr Somnath Chaudhuri (University of Southampton). Content is under a CC BY‑style permissive license and can be freely used for educational purposes with proper attribution.